no code implementations • NAACL (BioNLP) 2021 • Ravi Kondadadi, Sahil Manchanda, Jason Ngo, Ronan McCormack
This paper describes experiments undertaken and their results as part of the BioNLP MEDIQA 2021 challenge.
no code implementations • EAMT 2020 • Sahil Manchanda, Galina Grunin
Neural Machine Translation (NMT) is a deep learning based approach that has achieved outstanding results lately in the translation community.
no code implementations • 18 Oct 2023 • Rishi Shah, Krishnanshu Jain, Sahil Manchanda, Sourav Medya, Sayan Ranu
Second, we decouple the parameter space and the partition count making NeuroCUT inductive to any unseen number of partition, which is provided at query time.
1 code implementation • 14 Oct 2023 • Mridul Gupta, Sahil Manchanda, Hariprasad Kodamana, Sayan Ranu
GNNs, like other deep learning models, are data and computation hungry.
1 code implementation • 6 Jun 2023 • Sahil Manchanda, Shubham Gupta, Sayan Ranu, Srikanta Bedathur
Despite their initial success, these techniques, like much of the existing deep generative methods, require a large number of training samples to learn a good model.
no code implementations • 6 Jun 2023 • Shubham Gupta, Sahil Manchanda, Sayan Ranu, Srikanta Bedathur
In this work, we address these limitations through a novel GNN framework called GRAFENNE.
no code implementations • 29 Jan 2023 • Vaibhav Bihani, Sahil Manchanda, Srikanth Sastry, Sayan Ranu, N. M. Anoop Krishnan
Optimization of atomic structures presents a challenging problem, due to their highly rough and non-convex energy landscape, with wide applications in the fields of drug design, materials discovery, and mechanics.
no code implementations • 24 Aug 2022 • Sahil Manchanda, Sayan Ranu
In this work, we study the hitherto unexplored paradigm of Lifelong Learning to Branch on Mixed Integer Programs.
no code implementations • 1 Jun 2022 • Sahil Manchanda, Sofia Michel, Darko Drakulic, Jean-Marc Andreoli
Neural Combinatorial Optimization approaches have recently leveraged the expressiveness and flexibility of deep neural networks to learn efficient heuristics for hard Combinatorial Optimization (CO) problems.
1 code implementation • 7 Mar 2022 • Shubham Gupta, Sahil Manchanda, Srikanta Bedathur, Sayan Ranu
There has been a recent surge in learning generative models for graphs.
1 code implementation • NeurIPS 2021 • Jayant Jain, Vrittika Bagadia, Sahil Manchanda, Sayan Ranu
First, our study reveals that a significant portion of the routes recommended by existing methods fail to reach the destination.
no code implementations • 10 Jan 2020 • Sahil Manchanda, Arun Rajkumar, Simarjot Kaur, Narayanan Unny
The decision to rollout a vehicle is critical to fleet management companies as wrong decisions can lead to additional cost of maintenance and failures during journey.
2 code implementations • NeurIPS 2020 • Sahil Manchanda, Akash Mittal, Anuj Dhawan, Sourav Medya, Sayan Ranu, Ambuj Singh
Additionally, a case-study on the practical combinatorial problem of Influence Maximization (IM) shows GCOMB is 150 times faster than the specialized IM algorithm IMM with similar quality.
no code implementations • 15 May 2017 • Sahil Manchanda, Ashish Anand
Drug repositioning (DR) refers to identification of novel indications for the approved drugs.